I have a need to dequeue messages coming from an Oracle Queue on a continuous basis.
As far as I could imagine, we can deuque the message in two ways, either through Asyncronous Auto-Notification approach or by manual polling process where one can dequeue one message at a time.
I can't go for Asyncronous notification feature as the number of messages it receives could go upto 1000 within 5 mintues during peak hours and
I do not want to overload the database by spawning multiple callback procedures in the background.
With the manual polling process,I can create a one-time scheduler job that runs 24*7 which calls a stored proc that dequeus the messages in a loop in WAIT mode(kind of listening for a message).
The problem with this approach is that
1) the scheduler job runs continously and occupies one permanent job slot
2) the stored procedure does not EXIT as it runs in a loop waiting for messages.
Are there any alternative/better solutions where I do not need to have a job/procedure running continuously looking for messages?
Can I use auto-notification approach to get notification for the very first message,un-subscribe the subscriber and dequeue further messages and
subscribe to the queue again when there are no more messages ? Is this a safe approach and will i lose any message in between subscription and un-subscription ?
BTW, We use Oracle 10gR2 database, so I can't use PURGE ON NOTIFICATION option.
Appreciate your expert solution!!
You're right, it's not a good idea to use auto-notification for a high-volume queue.
At one client I've seen a one-time scheduler job which runs 24*7, it seems to work reasonably well, and they can enqueue a special "STOP" message (which goes to the top of the queue) that it listens for and stops processing messages.
However, generally I'd lean towards a job that runs regularly (e.g. once per minute, or whatever granularity is suitable for you) which would dequeue all the messages. I'd put the dequeue in a loop with a loop counter and a "maximum messages" limiter based on the maximum number of messages you'd expect in a 1-minute period. The job would keep processing messages until (a) there are no more messages in the queue, or (b) the maximum limit has been reached.
You can then set the schedule for the job based on the maximum delay you want to see between an enqueue and a dequeue. E.g. if it doesn't matter if a message isn't processed within 5 minutes, you could set the job to run once every 5 minutes.
The maximum limit needs to be quite a high figure - e.g. 10x or 100x the expected maximum number - otherwise a spike could flood your queue and it might not keep up. The idea of the maximum limit is to ensure that the job never runs forever. This should give ops enough time to detect a problem with the queue (e.g. if some rogue process is flooding the queue with bogus messages).
Related
I have multiple producers that stage objects (jobs) for processing, and a single consumer that takes objects one-by-one. I need to design a sort of a scheduler in golang.
Scheduling is asynchroneous, i.e. each producer works in a separate gorourine.
Scheduler interface is "good" in terms of golang-way (I'm new in Go).
A producer can remove or replace its staged object (if not yet consumed) with zero or minimal lost in the position in a queue. If a producer misses its slot because it canceled and then restaged an object, it still keeps a privilege to stage as soon as possible early till the end of the particular round.
"Fair" scheduling between producers.
Customizable multi-level weighting/prioritization
I'd like some hints and examples on right design of such a scheduler.
I feel I need every producer to wait for a token in a channel, then write (or don't write) an object to a shared consumer channel, then dispose the token, so it is routed to a next producer. Still, I'm not shure this is the best approach. Besides, it takes 3 sequential syncrhoneous operations per producer, so I'm afraid I'll have performance pitfalls because of the token traveling too slowly between producers. Also, 3 steps for one operation is probably not a good golang-way.
We are working on parallelising our Kafka consumer to process more number of records to handle the Peak load. One way, we are already doing is through spinning up as many consumers as many partitions within the same consumer group.
Our Consumer deals with making an API call which is synchronous as of now. We felt making this API call asynchronous will make our consumer handle more load. Hence, we are trying to making the API call Asynchronous and in its response we are increasing the offset. However we are seeing an issue with this:
By making the API call Asynchronous, we may get the response for the last record first and none of the previous record's API calls haven't initiated or done by then. If we commit the offset as soon as we receive the response of the last record, the offset would get changed to the last record. In the meantime if the consumer restarts or partition rebalances, we will not receive any record before the last record we committed the offset as. With this, we will miss out the unprocessed records.
As of now we already have 25 partitions. We are looking forward to understand if someone have achieved parallelism without increasing the partitions or increasing the partitions is the only way to achieve parallelism (to avoid offset issues).
First, you need to decouple (if only at first) the reading of the messages from the processing of these messages. Next look at how many concurrent calls you can make to your API as it doesn't make any sense to call it more frequently than the server can handle, asynchronously or not. If the number of concurrent API calls is roughly equal to the number of partitions you have in your topic, then it doesn't make sense to call the API asynchronously.
If the number of partitions is significantly less than the max number of possible concurrent API calls then you have a few choices. You could try to make the max number of concurrent API calls with fewer threads (one per consumer) by calling the API's asynchronously as you suggest, or you can create more threads and make your calls synchronously. Of course, then you get into the problem of how can your consumers hand their work off to a greater number of shared threads, but that's exactly what streaming execution platforms like Flink or Storm do for you. Streaming platforms (like Flink) that offer checkpoint processing can also handle your problem of how to handle offset commits when messages are processed out of order. You could roll your own checkpoint processing and roll your own shared thread management, but you'd have to really want to avoid using a streaming execution platform.
Finally, you might have more consumers than max possible concurrent API calls, but then I'd suggest that you just have fewer consumers and share partitions, not API calling threads.
And, of course, you can always change the number of your topic partitions to make your preferred option above more feasible.
Either way, to answer your specific question you want to look at how Flink does checkpoint processing with Kafka offset commits. To oversimplify (because I don't think you want to roll your own), the kafka consumers have to remember not only the offsets they just committed, but they have to hold on to the previous committed offsets, and that defines a block of messages flowing though your application. Either that block of messages in its entirety is processed all the way through or you need to rollback the processing state of each thread to the point where the last message in the previous block was processed. Again, that's a major oversimplification, but that's kinda how it's done.
You have to look at kafka batch processing. In a nutshell: you can setup huge batch.size with a little number (or even single) of partitions. As far, as whole batch of messages consumed at consumer side (i.e. in ram memory) - you can parallelize this messages in any way you want.
I would really like to share links, but their number rolls over the web hole.
UPDATE
In terms of committing offsets - you can do this for whole batch.
In general, kafka doesn't achieve target performance requirements by abusing partitions number, but rather relying on batch processing.
I already saw a lot of projects, suffering from partitions scaling (you may see issues later, during rebalancing for example). The rule of thumb - look at every available batch setting first.
When StreamListener is taking a long time (longer than max.poll.interval.ms) to process a message, thus that particular consumer is occupied and other new messages will be assigned to other partitions. After the time is greater than max.poll.interval.ms, rebalance happened and the same situation will happened to another consumer. So this message will circulate around all the partitions and keep on hogging the resources.
However, this situation is not happening very often, only a few messages somehow is taking such a long time to process and it's uncontrollable.
Can we commit the offset and throw it to DLQ after a few times of rebalancing? If yes, how can we do that? If no, what's the proper handling for this kind of situation?
Increasing max.poll.interval.ms will have no impact on performance (except it will take longer to detect a consumer that is really dead).
Going through a rebalance each time you process this "bad" record is much more damaging to performance.
You can, however, do what you want with a custom SeekToCurrentErrorHandler together with a recoverer such as the DeadLetterPublishingRecoverer. You would also need a rebalance listener to count the rebalances and some mechanism to share the state from the error handler across instances (the standard one only keeps state in memory).
Quite complicated, I think.
I have a single producer and n workers that I only want to give work to when they're not already processing a unit of work and I'm struggling to find a good zeroMQ pattern.
1) REQ/REP
The producer is the requestor and creates a connection to each worker. It tracks which worker is busy and round-robins to idle workers
Problem:
How to be notified of responses and still able to send new work to idle workers without dedicating a thread in the producer to each worker?
2) PUSH/PULL
Producer pushes into one socket that all workers feed off, and workers push into another socket that the producer listens to.
Problem:
Has no concept of worker idleness, i.e. work gets stuck behind long units of work
3) PUB/SUB
Non-starter, since there is no way to make sure work doesn't get lost
4) Reverse REQ/REP
Each worker is the REQ end and requests work from the producer and then sends another request when it completes the work
Problem:
Producer has to block on a request for work until there is work (since each recv has to be paired with a send ). This prevents workers to respond with work completion
Could be fixed with a separate completion channel, but the producer still needs some polling mechanism to detect new work and stay on the same thread.
5) PAIR per worker
Each worker has its own PAIR connection allowing independent sending of work and receipt of results
Problem:
Same problem as REQ/REP with requiring a thread per worker
As much as zeroMQ is non-blocking/async under the hood, I cannot find a pattern that allows my code to be asynchronous as well, rather than blocking in many many dedicated threads or polling spin-loops in fewer. Is this just not a good use case for zeroMQ?
Your problem is solved with the Load Balancing Pattern in the ZMQ Guide. It's all about flow control whilst also being able to send and receive messages. The producer will only send work requests to idle workers, whilst the workers are able to send and receive other messages at all times, e.g. abort, shutdown, etc.
Push/Pull is your answer.
When you send a message in ZeroMQ, all that happens initially is that it sits in a queue waiting to be delivered to the destination(s). When it has been successfully transferred it is removed from the queue. The queue is limited in length, but can be set by changing a socket's high water mark.
There is a/some background thread(s) that manage all this on your behalf, and your calls to the ZeroMQ API are simply issuing instructions to that/those threads. The threads at either end of a socket connection are collaborating to marshall the transfer of messages, i.e. a sender won't send a message unless the recipient can receive it.
Consider what this means in a push/pull set up. Suppose one of your pull workers is falling behind. It won't then be accepting messages. That means that messages being sent to it start piling up until the highwater mark is reached. ZeroMQ will no longer send messages to that pull worker. In fact AFAIK in ZeroMQ, a pull worker whose queue is more full than those of its peers will receive less messages, so the workload is evened out across all workers.
So What Does That Mean?
Just send the messages. Let 0MQ sort it out for you.
Whilst there's no explicit flag saying 'already busy', if messages can be sent at all then that means that some pull worker somewhere is able to receive it solely because it has kept up with the workload. It will therefore be best placed to process new messages.
There are limitations. If all the workers are full up then no messages are sent and you get blocked in the push when it tries to send another message. You can discover this only (it seems) by timing how long the zmq_send() took.
Don't Forget the Network
There's also the matter of network bandwidth to consider. Messages queued in the push will tranfer at the rate at which they're consumed by the recipients, or at the speed of the network (whichever is slower). If your network is fundamentally too slow, then it's the Wrong Network for the job.
Latency
Of course, messages piling up in buffers represents latency. This can be restricted by setting the high water mark to be quite low.
This won't cure a high latency problem, but it will allow you to find out that you have one. If you have an inadequate number of pull workers, a low high water mark will result in message sending failing/blocking sooner.
Actually I think in ZeroMQ it blocks for push/pull; you'd have to measure elapsed time in the call to zmq_send() to discover whether things had got bottled up.
Thought about Nanomsg?
Nanomsg is a reboot of ZeroMQ, one of the same guys is involved. There's many things I prefer about it, and ultimately I think it will replace ZeroMQ. It has some fancier patterns which are more universally usable (PAIR works on all transports, unlike in ZeroMQ). Also the patterns are essentially a plugable component in the source code, so it is far simpler for patterns to be developed and integrated than in ZeroMQ. There is a discussion on the differences here
Philisophical Discussion
Actor Model
ZeroMQ is definitely in the realms of Actor Model programming. Messages get stuffed into queues / channels / sockets, and at some undetermined point in time later they emerge at the recipient end to be processed.
The danger of this type of architecture is that it is possible to have the potential for deadlock without knowing it.
Suppose you have a system where messages pass both ways down a chain of processes, say instructions in one way and results in the other. It is possible that one of the processes will be trying to send a message whilst the recipient is actually also trying to send a message back to it.
That only works so long as the queues aren't full and can (temporarily) absorb the messages, allowing everyone to move on.
But suppose the network briefly became a little busy for some reason, and that delayed message transfer. The message send might then fail because the high water mark had been reached. Whoops! No one is then sending anything to anyone anymore!
CSP
A development of the Actor Model, called Communicating Sequential Processes, was invented to solve this problem. It has a restriction; there is no buffering of messages at all. No process can complete sending a message until the recipient has received all the data.
The theoretical consequence of this was that it was then possible to mathematically analyse a system design and pronounce it to be free of deadlock. The practical consequence is that if you've built a system that can deadlock, it will do so every time. That's actually not so bad; it'll show up in testing, not post-deployment.
Curiously this is hinted at in the documentation of Microsoft's Task Parallel library, where they advocate setting buffer lengths to zero in the intersts of achieving a more robust application.
It'd be like setting the ZeroMQ high water mark to zero, but in zmq_setsockopt() 0 means default, not nought. The default is non-zero...
CSP is much more suited to real time applications. Any shortage of available workers immediately results in an inability to send messages (so your system knows it's failed to keep up with the real time demand) instead of resulting in an increased latency as data is absorbed by sockets, etc. (which is far harder to discover).
Unfortunately almost every communications technology we have (Ethernet, TCP/IP, ZeroMQ, nanomsg, etc) leans towards Actor Model. Everything has some sort of buffer somewhere, be it a packet buffer on a NIC or a socket buffer in an operating system.
Thus to implement CSP in the real world one has to implement flow control on top of the existing transports. This takes work, and it's slightly inefficient. But if a system that needs it, it's definitely the way to go.
Personally I'd love to see 0MQ and Nanomsg to adopt it as a behavioural option.
I have a queue that is loaded with high priority JMS messages throughout the day, I want to get them out the door quickly. The queue is also being loaded periodically with lower priority messages in large batches. The problem that I see on busy days, is that there are always enough high priority messages at the front of the queue that none of the lower priority messages get selected until that volume drops off. Often they will sit on the queue until they middle of the night. The app is distributed over a number of servers, but the CPUs are not even breathing hard, the JMS seems to be the choak point.
My hunch is to implement some sort of aging algorithm that increases priority for messages that have been on the queue for a very long time, but of course, that is what middleware is supposed to do for me. I can't imagine that the JMS provider (IBM WebsphereMQ) or the application server (TIBCO BusinessWorks) doesn't have some sort of facility to cope with this. So before I go write some code, I thought I would ask, is there any way to get either of these technologies to help me out with this problem?
The BusinessWorks activity that is reading the queue is a JMS SOAP Event Source, but I could turn it into a JMS Queue Receiver activity or whatever.
All thoughts on how to solve this are welcome :-) TIA
That's like tying 1 hand behind your back and then complaining that you cannot swim properly. D'oh! First off, who's bright idea was it to mix messages. Just because you can do something does not mean you should.
The app is distributed over a number of servers, but the CPUs are not
even breathing hard, the JMS seems to be the choak point.
Well then, the solution is easy. Put high priority messages into queue "A" (the existing queue) and low priority messages into a new queue "B". Next, startup another instance of your JMS application to read the messages off queue "B".
Also, JMS is probably not the choke-point. It is what the application is doing with the message data after the JMS layer picks up the message that is taking a long time (i.e. backend work).
Finally, how many instances of your JMS application is running against the existing queue? If you are only running 1 instance, why? If you have lots of CPU capacity then why don't you run 10 instances of your JMS application. Do some true parallel processing of messages.
If you really want to keep you messages mixed on the same queue and have the high priority messages processed first, and yet your volume of messages is such that you cannot work through all the volume sometimes until the middle of the night, then you quite simply do not have enough processing applications. MQ is a parallel processing system, it is designed to allow many applications to put or get from a queue at once. Make use of this by running more of your getting applications at the same time. They will work through your high priority messages quicker and then get back to processing the lower priority ones.
From your description it's clear that you want the high priority messages to processed first. In such a case lower priority messages will have to wait.
MQ will not increase the priority of messages if they are sitting in queue for long time. How will it know that it has to change property of a message :)?. You will need to develop an application to do that.
I would think segregating messages based on priority, for example, high priority messages are put to one queue and lower priority messages to another queue could be one option you could look at.
Second option would be to look at the changing the delivery sequence (MSGDLVSQ) to FIFO. This makes to messages to be delivered to consumers in the order they arrived into queue. But note this will ignore the message priority, meaning if there is a lower priority message followed by a higher priority message, then higher priority message will wait till the lower priority message is delivered.